Skip to content
Agentmart
Submit a tool

reviewing-code

Reviews a diff or file for bugs, security issues, and missing tests, returning prioritized findings.

Skill by matthewhand

IndexedMIT★ 20
Write a review

Install

Works with Claude Code, Claude apps, Codex, Cursor, Gemini CLI, GitHub Copilot, VS Code, OpenCode, Goose, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install skill/matthewhand-reviewing-code

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Reviews a diff or file for bugs, security issues, and missing tests, returning prioritized findings. Use when the user asks for a code review, a PR review, or "what's wrong with this code".

Use cases: security

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this skill can do and what it asks for, from its SKILL.md. Checked Oct 25, 2026.

Tools
No tools found
Secrets
None asked for
Install scripts
None found

Network hosts it talks to 1

  • codeload.github.com · found in install command

Files it touches

  • ~/.claude/skills/reviewing-code

What's inside

Skill name
reviewing-code
Description
Reviews a diff or file for bugs, security issues, and missing tests, returning prioritized findings. Use when the user asks for a code review, a PR review, or "what's wrong with this code".
License
MIT
Instructions
29 lines in SKILL.md · view on GitHub

Files (1)

  • SKILL.md

SKILL.md (first lines)

# Reviewing Code

Review the supplied diff or file and report concrete, actionable findings.
Prefer a few high-signal issues over an exhaustive list of nitpicks.

## Process

1. Read the change and infer its intent.
2. Look, in priority order, for:
   - **Correctness** — logic errors, off-by-one, wrong/missing error handling,
     unhandled `None`/null, race conditions, resource leaks.
   - **Security** — injection, path traversal, secrets in code, unsafe
     deserialization, missing authz/authn checks.
   - **Tests** — untested new behavior; the specific case that would catch a bug.
   - **Clarity** — naming, dead code, or duplication that will mislead the next
     reader. Only if it materially hurts maintainability.
3. Skip style a linter/formatter already enforces.

## Output

For each finding, one bullet:

`- [severity] file:line — problem, then the fix in one clause.`

Use severity `blocker`, `major`, or `minor`. End with a one-line verdict:
`APPROVE`, `APPROVE WITH NITS`, or `REQUEST CHANGES`. If you find nothing
substantive, say so plainly rather than inventing issues.

From matthewhand/operating-swarm, MIT.

More from matthewhand/operating-swarm

Signals

Stars
20
Forks
6
Open issues
1
Last commit (this folder)
Jun 17, 2026 (4 months ago)
Last release
Jun 19, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

License
MIT
First seen
Oct 24, 2026
Last checked
Oct 24, 2026

More from matthewhand

Cite this page

reviewing-code skill. Agent Mart. https://agentmart.dev/skills/matthewhand-reviewing-code (last updated 2026-10-24)